一种用于服务质量预测的混合协同过滤方法

A Hybrid Collaborative Filtering Approach for Service Qo S Prediction

不同用户的网络状况、异构环境和地理位置的不同导致其对相同Web服务感受到的Qo S差异较大,因此提出了一种为用户预测其未调用过服务的Qo S的混合协同过滤方法。首先采用皮尔逊相关系数计算服务之间的相似度,并引入相似度信任因子对相似度进行修正,然后得到与目标服务最相似的top-k服务近邻集,最后采用改进的协同过滤方法预测目标服务的Qo S值。采用网络上真实服务的Qo S数据集进行实验评估,实验结果表明,该方法可有效提升Qo S预测的准确度。

The QoS of web service may vary widely for different users due to their different network conditions, heterogeneous environments and locations.In this paper, a hybrid collaborative filtering approach was proposed for QoS prediction.Firstly, Pearson Correlation Coefficient was employed to measure the similarity between two services to find the top-k similar neighbors for target service.Then, the similarity was modified by employing similarity trustworthy factor.Finally, the traditional collabora-tive filtering method was modified to predict the QoS of target service.Real world QoS data were obtained to evaluate the ap-proach.The experimental results demonstrate that the prediction accuracy of QoS could be effectively improved.